Article

Video Prediction Policy 2: Event-Level Video Pretraining Improves Manipulation Policy Generalization

The authors propose the world action model Video Prediction Policy 2 (VPP2), which uses event-level pretraining on large-scale manipulation video, distills the video model into a single-step visual planner, and connects an action module via a MoT architecture to learn implicit inverse dynamics.

Part of the event: VPP2 World Action Model Paper Released

This page provides a summary and source link only.